© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71598
    Prev
    Next
    INDEX
    Explanations

    methods, attributes, and defining classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    0.43
    jourd
    0.39
    germeister
    0.39
    koľ
    0.39
    별
    0.38
     ferv
    0.38
     целый
    0.38
    ع
    0.38
     exemplary
    0.38
     현대
    0.38
    POSITIVE LOGITS
     costing
    0.52
     denote
    0.50
     &=\
    0.50
     augmente
    0.49
    ಾದರೂ
    0.48
     resizing
    0.46
     eraser
    0.46
     জানার
    0.45
     avaient
    0.45
    াটো
    0.45
    Activations Density 0.006%

    No Known Activations